Reference documentation and code samples for the Vertex AI V1 API class Google::Cloud::AIPlatform::V1::RagEmbeddingModelConfig.
Config for the embedding model to use for RAG.
Inherits
- Object
Extended By
- Google::Protobuf::MessageExts::ClassMethods
Includes
- Google::Protobuf::MessageExts
Methods
#vertex_prediction_endpoint
def vertex_prediction_endpoint() -> ::Google::Cloud::AIPlatform::V1::RagEmbeddingModelConfig::VertexPredictionEndpoint
Returns
- (::Google::Cloud::AIPlatform::V1::RagEmbeddingModelConfig::VertexPredictionEndpoint) — The Vertex AI Prediction Endpoint that either refers to a publisher model or an endpoint that is hosting a 1P fine-tuned text embedding model. Endpoints hosting non-1P fine-tuned text embedding models are currently not supported. This is used for dense vector search.
#vertex_prediction_endpoint=
def vertex_prediction_endpoint=(value) -> ::Google::Cloud::AIPlatform::V1::RagEmbeddingModelConfig::VertexPredictionEndpoint
Parameter
- value (::Google::Cloud::AIPlatform::V1::RagEmbeddingModelConfig::VertexPredictionEndpoint) — The Vertex AI Prediction Endpoint that either refers to a publisher model or an endpoint that is hosting a 1P fine-tuned text embedding model. Endpoints hosting non-1P fine-tuned text embedding models are currently not supported. This is used for dense vector search.
Returns
- (::Google::Cloud::AIPlatform::V1::RagEmbeddingModelConfig::VertexPredictionEndpoint) — The Vertex AI Prediction Endpoint that either refers to a publisher model or an endpoint that is hosting a 1P fine-tuned text embedding model. Endpoints hosting non-1P fine-tuned text embedding models are currently not supported. This is used for dense vector search.